An educational tutorial to showcase Computer Aided Drug Discovery (CADD) in the classroom. The interactive Jupyter Notebooks are designed for teaching purposes and lead the user through a simplifed virtual compound screening pipeline.
Our tutorial runs through an example of the protein estrogen receptor (PDB ID: 1G50) which is important in the breast cancer setting. Using a data subset from the ChEMBL database, we apply a random forest predictor to identify new lead compounds from a mock dataset and their potential in binding to estrogen receptor.
The easist way to setup an environment for this project is to use conda package manager
conda env create -f environment.yml
To activate the environment conda activate CADD
You can run the notebook in binder by following this link. Note that binder will spawn a new container when you launch the notebook so it can take a while :)
You can run the notebook in colab by following this link. You may need to install some additional modules when running in colab, you can do so by using '!pip'.
This project was coded during the Life Science Hackathon 2019 in London.
Contributers are:
Jonathan Ish-Horowicz
Daniel Jiang
Léonie Strömich
Tony Yang